A5046534919- Anomaly Detection Techniques and Applications
- Context-Aware Activity Recognition Systems
- EEG and Brain-Computer Interfaces
- Modeling, Simulation, and Optimization
- Simulation Techniques and Applications
- Non-Invasive Vital Sign Monitoring
- Advanced Neural Network Applications
- Clostridium difficile and Clostridium perfringens research
- Occupational Health and Safety Research
- Multi-Agent Systems and Negotiation
- ECG Monitoring and Analysis
- Fire Detection and Safety Systems
Warsaw University of Technology
2022-2023
Systems Research Institute
2022-2023
Polish Academy of Sciences
2022-2023
Medical University of Silesia
2023
Continuous, real-time monitoring of occupational health and safety in high-risk workplaces such as construction sites can substantially improve the workers. However, introducing systems practice is associated with a number challenges, scaling up solution while keeping its cost low. In this context, work investigates use an off-the-shelf, low-cost smartwatch to detect issues based on heart rate privacy-preserving manner. To smartwatch’s low measurement quality, novel, frugal machine learning...
Fall accidents in industrial and construction environments require an immediate reaction, to provide first aid. Shortening the time between fall relevant personnel being notified can significantly improve safety health of workers. Therefore, this work, IoT system for real-time detection is proposed, using ASSIST-IoT reference architecture. Empowered with a machine learning model, detect swiftly notify occupational manager. To train novel multimodal dataset was collected from ten human...
Detecting Personal Protective Equipment in images and video streams is a relevant problem ensuring the safety of construction workers. In this contribution, an architecture enabling live image recognition such equipment proposed. The solution deployable two settings -- edge-cloud edge-only. system was tested on active site, as part larger scenario, within scope ASSIST-IoT H2020 project. To determine feasibility edge-only variant, model for counting people wearing helmets developed using...
While agent-based models and simulations materialize in multiple areas, the existing simulation-focused agent platforms require in-depth programming knowledge, or are overly simplistic. In this context, Agents Assembly (AASM) domain-specific language platform have been recently proposed. The AASM ecosystem is highly scalable, as software stack allows its straightforward deployment on networked computers (physical virtual machines). has designed to capture key concepts, needed run...